Decent enough for a model 50 times smaller than ChatGPT. I use orca_mini_3b.
acec
joined 2 years ago
Compile llama.cpp, download a small GGML LLM model and you will have a quite intelligent assiatant running into your phone.
I still don't understand why the developer does not consider the option of adding a custom API key
It is not that I think that are hard to refill, it is that I actually tried to refill them. Horrible experience. Also, even using a good coffee brand, the result is not optimal.
And you loose all the convenience of using capsules. They are dirty and difficult to refill, also the quality of the resulting coffee cup is horrible compared to nespresso capsules. A regular italian expresso machine is a better option: awesome quality, you can choose the coffee brand and it is easier to refill than a reusable capsule.
Can we say genocide already?